Skip to content
Nappai Documentation

Simple Report Agent

Simple Report Agent writes reports in conversation. You ask for a report on a topic and the agent plans its structure, researches each section with the tools you connect, writes it and, at the end, puts all the sections together into one document. If there is data in tables, it can add charts.

Depending on the format you choose, the report appears directly in the chat or is delivered as a PDF or HTML file saved to the conversation, with its download link. Because it is an agent, you can keep talking to it to ask for changes or a new report.

When to use it

  • You want your team to ask for reports from the chat without setting anything up each time.
  • You need a report that combines information from several sources, such as the web and your knowledge base.
  • A coordinating agent has to hand the writing part to a report specialist.
  • You want reports with a fixed structure for their type: executive summary, business analysis, project report.

Configuration

FieldWhat it does
Agent NameThe agent’s name. It is used when you connect it as a tool or as an agent of another agent. Default: ReportAgent.
Agent DescriptionWhat the agent does, in one sentence. It helps other agents decide when to use it.
User PromptThe text the agent receives. Default: {input}, which is replaced by whatever arrives at Input. You can add other variables in curly braces; each one appears as a new field.
System PromptThe agent’s general instructions. It comes with instructions ready for writing professional reports; you can adapt them, for example to set the tone or the sections you always want.
InputThe user’s request, usually connected from a Chat Input.
ConnectionWhat to connect
Model (required)The AI model that plans and writes, for example OpenAI or Anthropic.
ToolsThe tools the agent researches with, for example web search or a lookup in your knowledge base. Without tools, the report is limited to what the AI model knows.

Advanced options

FieldWhat it does
Report TypeThe type of report, which decides its structure: executive_summary, technical_report, research_report, business_analysis, project_report or custom (general structure). Default: research_report.
Output FormatHow the report is delivered: markdown (shown in the chat), pdf or html (the file is produced and the answer includes the link). Default: markdown.
Enable Chart GenerationCreates charts from the data in the report’s tables. Default: on.
Use memoryMakes the agent remember the conversation, so you can ask for changes to the previous report. When you turn it on, the Memory connection appears, where you can connect a memory component such as Postgres Memory. Default: off.
StreamShows the answer in the chat as it is generated. Default: off.
Enable Progress StreamingWith Stream on, shows progress notices for each phase of the report. Default: on.
Recursion LimitThe maximum number of internal steps the agent can take for each answer. Default: 1000.

Batch processing

With the Batch Mode switch on, the component runs once for each item of the list you connect to Batch Input and returns all the results together as a list. Parallel Executions sets how many items are processed at the same time (1 to 5). Skip if Empty Batch Input skips the component when the list arrives empty, and Skip Branch if Empty Output stops the following components when the result is empty. More in Key concepts.

Using it as an agent tool

You can connect this component to an agent’s Tools input. In the Tool tab, Tool Name and Tool Description are the name and explanation the agent uses to recognise the tool and decide when to call it: write a clear description of what it does.

Output

  • Response: the agent’s answer: the whole report in the chat or the link to the PDF or HTML file. Connect it to a Chat Output.
  • Agent: the whole agent, to connect it to another component that coordinates agents, such as Planner Executor Agent.
  • Tool: the agent as a tool, to connect it to another agent’s Tools input.

Example

A real estate agency wants its sales staff to ask for neighbourhood reports from the chat.

  1. Connect an AI model to Model and a web search tool to Tools.
  2. In the advanced options, choose business_analysis in Report Type and pdf in Output Format.
  3. Connect a Chat Input to Input and Response to a Chat Output.
  4. A salesperson writes: Report on the housing market in the Ruzafa neighbourhood of Valencia: prices, supply and services.

The agent researches, writes the report section by section and answers with the link to the PDF.

Good practices

  • Connect at least one search or lookup tool: without them, the report cannot include current data.
  • Check the report’s figures before sharing it.